Qwen 3.8 Coding Test: Nearly Matches K3 at Half the Price
bindureddy · x · 2026-08-04
A developer shared preliminary test results for the Qwen 3.8 model. It performs well in agentic coding tasks, being only slightly worse than the K3 model but twice as cheap, making it the top model in its price range. The author suggests switching from K3 to Qwen 3.8 to cut costs.
Related event: Alibaba's Qwen3.8-Max: Open-Source Model Nears Closed-Source Frontier(13 posts)→
More from coding & agent
- Simon Willison: code mode is the future of tool calling, if it can be sandboxed — springrod · 2026-10-16
- Dev workflow: Astra for tedious tasks, Claude for ideas not implementation — menhguin · 2026-10-16
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16